Paper2Agent converts research papers into interactive AI agents, enabling complex scientific queries and collaboration with over 80% accuracy in reproducing original results.
- Open access
- 3 cites
Moving in Nature, Science.
Rebuilt
Paper2Agent converts research papers into interactive AI agents, enabling complex scientific queries and collaboration with over 80% accuracy in reproducing original results.
Biomni, a versatile AI agent, autonomously performs diverse biomedical research tasks with high accuracy across 25 domains, accelerating discovery processes.
Newest first · last 60 days
Engineering translation control enables predictable gene expression by tuning initiation, elongation, and termination processes in biological systems.
Protein interaction networks in a mouse tauopathy model undergo significant, phosphorylation-dependent remodeling, with over 20 key complexes showing dynamic changes during disease progression.
Embeddings from genome and protein language models enable high-resolution, alignment-free insights into genomics and proteomics, surpassing traditional methods.
Genolator, a multimodal large language model, achieves over 365,000 question-answer pairs to accurately interpret protein functions from genomic and structural data.
Paper2Agent converts research papers into interactive AI agents, enabling complex scientific queries and collaboration with over 80% accuracy in reproducing original results.
A structured methodological framework enables early-stage performance assessment of clinical variant classification platforms, demonstrated on 97 cases across three versions.
Gene Ontology priors in biologically-informed neural networks mainly organize activations into meaningful units rather than improving performance, with the most promising approach being soft-link encoders.
Large language models accessing the DGIdb API via the MCP server significantly enhance their ability to answer up-to-date biomedical questions about the druggable genome.
Novel document-level uncertainty aggregation strategies significantly improve active learning performance in ontology curation, with KPSum showing consistent gains over random sampling.
CIViC-Fact reveals that less than 30% of cancer variant claims can be fully validated from abstracts alone, emphasizing the need for full-text evaluation in biomedical verification.
EcoXAI's multi-agent system identified 79 novel drug candidates for Alzheimer's Disease, surpassing randomized baselines and supporting literature validation.
Large language models with trillions of parameters are transforming bioinformatics by enhancing analysis and understanding of complex biological systems.
AutoBioKG constructs highly accurate, context-aware biomedical knowledge graphs, outperforming baselines by 3.6-17.8 percentage points in zero-shot F1 across multiple datasets.
Biomni, a versatile AI agent, autonomously performs diverse biomedical research tasks with high accuracy across 25 domains, accelerating discovery processes.
PubMind extracts and annotates over 1.3 million genetic variants from biomedical literature with high accuracy, revealing many novel variants beyond existing databases.
Automated pipeline using large language models identified 6,802 gene perturbation signatures from 4,453 GEO experiments, covering 2,907 genes with high accuracy.
Journals this month
Moving areas, week to 3 Oct 2026